{ "model": "/workspace/distill_student_init10", "data_dir": "/workspace/distill_cache/mixed_external_behavior_expanded_plus.jsonl.gz", "output_dir": "/workspace/distill_runs/external-behavior-expanded-plus-run6", "seq_len": 2048, "epochs": 1, "lr": 2.5e-05, "batch_size": 1, "grad_accum_steps": 8, "lora_r": 16, "lora_alpha": 32, "target_modules": [ "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj" ], "total_params": 8651684096, "trainable_params": 19922944, "train_samples": 1557, "eval_samples": 81, "load_in_4bit": true, "teacher_temperature": 1.0, "resume_adapter": "/workspace/distill_runs/external-behavior-expanded-plus-run5/adapter", "eval_only": false, "eval_loss": 0.8480964277030696, "eval_ppl": 2.3351974012631542, "final_adapter_dir": "/workspace/distill_runs/external-behavior-expanded-plus-run6/adapter", "metrics_path": "/workspace/distill_runs/external-behavior-expanded-plus-run6/metrics.jsonl" }